© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 11752
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically different types of apostrophes and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    檚
    -0.80
    principalTable
    -0.58
     CURIAM
    -0.58
    outSlope
    -0.50
    RectangleBorder
    -0.50
     مشين
    -0.50
     propOrder
    -0.49
    etí
    -0.48
    ----</
    -0.48
    UnusedPrivate
    -0.47
    POSITIVE LOGITS
    t
    2.02
    tand
    0.84
    tk
    0.84
     t
    0.81
    tend
    0.80
    tly
    0.78
    tA
    0.76
    tant
    0.76
    tw
    0.74
    tj
    0.74
    Activations Density 0.121%

    No Known Activations